Structured product labeling improves detection of drug-intolerance issues

Extracting drug indication information from structured product labels using natural language processing

OBJECTIVE

To extract drug indications from structured drug labels and represent the information using codes from standard medical terminologies.

MATERIALS AND METHODS

We used MetaMap and other publicly available resources to extract information from the indications section of drug labels. Drugs and indications were encoded by RxNorm and UMLS identifiers respectively. A sample was manually reviewed. We also compared the results with two independent information sources: National Drug File-Reference Terminology and the Semantic Medline project.

RESULTS

A total of 6797 drug labels were processed, resulting in 19 473 unique drug-indication pairs. Manual review of 298 most frequently prescribed drugs by seven physicians showed a recall of 0.95 and precision of 0.77. Inter-rater agreement (Fleiss κ) was 0.713. The precision of the subset of results corroborated by Semantic Medline extractions increased to 0.93.

DISCUSSION

Correlation of a patient's medical problems and drugs in an electronic health record has been used to improve data quality and reduce medication errors. Authoritative drug indication information is available from drug labels, but not in a format readily usable by computer applications. Our study shows that it is feasible to use publicly available natural language processing resources to extract drug indications from drug labels. The same method can be applied to other sections of the drug label-for example, adverse effects, contraindications.

CONCLUSIONS

It is feasible to use publicly available natural language processing tools to extract indication information from freely available drug labels. Named entity recognition sources (eg, MetaMap) provide reasonable recall. Combination with other data sources provides higher precision.

Consistency in the safety labeling of bioequivalent medications

PURPOSE

Bioequivalent medications are required by the Food and Drug Administration to have identical warnings on their labels. This requirement has both clinical and legal importance, yet has never been validated. We sought to determine the real-world consistency of electronic labeling for bioequivalent drugs from different manufacturers.

METHODS

Using natural language processing, we indexed the adverse drug reactions (ADRs) found in the Adverse Reactions and Post-Marketing sections of 9105 structured product labels. We calculated the standard deviation in ADR labeling for each bioequivalent drug and the percent deviation of each generic label from its corresponding brand. We also analyzed the performance of individual generic manufacturers. For the 25 drugs with the greatest discrepancy in labeled ADRs, we performed manual review to identify causes of inconsistency.

RESULTS

68% of multi-manufacturer drugs had discrepancies in ADR labeling. For a given drug, the mean deviation in number of labeled ADRs was 4.4, and the median was 0.8 (IQR 0 to 3.2). The mean range in number of labeled ADRs was 12 +/- 0.9, and the median was 2 (IQR 0 to 9). Overall, 77.9% of generic manufacturers produced labels differing from brand. Causes of inconsistency included missing tables, outdated post-marketing reports, and formatting issues.

CONCLUSIONS

Despite FDA mandate, bioequivalent drugs often differ in their safety labeling. Physicians should be aware of such differences and regulators should consider new strategies for harmonizing bioequivalent labels.